LLMs and AI Engineering covers: Build a Large Language Model, AI Engineering, LLM Engineer's Handbook, Patterns of Application Development Using AI. Understand large language models from the inside, then learn to build production applications with them. This is the frontier — where the industry is right now, and where the highest-leverage opportunities are. This is like learning Rails 8 with Hotwire — the newest, most exciting layer of the stack, built on top of everything you already learned. Book 1 (Build a LLM) is like Rebuilding Rails — you understand the framework by building it from scratch. Books 2-4 are like your Rails architecture books — patterns for building real applications with the technology.
This course unlocks once you've finished its prerequisite. Open prerequisite →
I need to be especially honest here because this module is about the technology that I am. I am a large language model. You are working through a curriculum built to understand ho…
You have shipped features with an LLM API by now, or you are about to. Here is the uncomfortable part: if someone asked you what actually happens between your prompt going in and …
There is a moment in every LLM project where the demo works, everyone is excited, and then someone asks the question that separates demos from products: "how do we know it's good?…
The previous book gave you judgment; the question it leaves open is muscle. When someone on your team says "let's fine-tune a small model on our support transcripts and serve it o…
Every book in this course so far spoke Python. This one speaks your language — literally. Its working code is Ruby, its author wrote The Rails Way, and its question is the one you…
Work through each item before the checkpoint.
Build retrieval-augmented generation from its parts: chunk a knowledge base, embed it, retrieve the right context for a question, assemble the prompt, generate an answer through a…
7 lessons. Read in order; spiral back when you need to. By the end you'll have used the core ideas twice — once on the abstract, once on something you'll meet at work next week.